A pure NumPy implementation of Mamba
github.com
A pure NumPy implementation of Mamba
1–10 of 39 posts
Re: A pure NumPy implementation of Mamba
#2Why is it so difficult to write a short description what the project does? With too many open source projects people, who are not familiar with it, have to play detective to figure out what it actually is doing. "Wait a package manager based on numphy? That doesn't make any sense. Oh they mention LLM? So it must have something to do with AI"
Re: A pure NumPy implementation of Mamba
#3Why is it so difficult to write a short description what the project does? With too many open source projects people, who are not familiar with it, have to play detective to figure out what it actually is doing. "Wait a package manager based on numphy? That doesn't make any sense. Oh they mention LLM? So it must have something to do with AI"
realistically, it's like a classification problem
at this moment, in this time, if you see Mamba, either you know or you don't
Re: A pure NumPy implementation of Mamba
#4Why is it so difficult to write a short description what the project does? With too many open source projects people, who are not familiar with it, have to play detective to figure out what it actually is doing. "Wait a package manager based on numphy? That doesn't make any sense. Oh they mention LLM? So it must have something to do with AI"
That's a fair criticism of many open source projects, however this one does link to the Mamba paper at the bottom of the (short) readme.
Re: A pure NumPy implementation of Mamba
#5Totally unclear what this is. I scrolled through the readme and it didn't even mention once what it does.
Re: A pure NumPy implementation of Mamba
#6Totally unclear what this is. I scrolled through the readme and it didn't even mention once what it does.
It totally mentions what it does. It takes the sentence "I have a dream that" and extends it to: "I have a dream that I will be able to see the sunrise in the morning."
It's an LLM.
Re: A pure NumPy implementation of Mamba
#7Why is it so difficult to write a short description what the project does? With too many open source projects people, who are not familiar with it, have to play detective to figure out what it actually is doing. "Wait a package manager based on numphy? That doesn't make any sense. Oh they mention LLM? So it must have something to do with AI"
The author did not post it to HN to confuse you. He did not post it here, at all.
Why are you entitled to have every single GitHub repo explained, tailored to your individual knowledge?
Many other people understood exactly what this is.
Maybe the submitter could add a comment on HN with an explanation, but the author owes you nothing.
Re: A pure NumPy implementation of Mamba
#8Totally unclear what this is. I scrolled through the readme and it didn't even mention once what it does.
It totally mentions what it does. It takes the sentence "I have a dream that" and extends it to: "I have a dream that I will be able to see the sunrise in the morning." It's an LLM.
It’s much more than just an LLM. The mamba architecture is often used in the backbone of an LLM but you can use it more generally as a linear-time (as opposed to quadratic-time) sequence modeling architecture (as per the original paper’s title, which is cited in the linked repo). It is much closer to a convolutional network or an RNN (it has bits of both) than to a transformer architecture. It is based off the notion of state spaces (with a twist).
I use Mamba for instance to build surrogate models of physics-based building energy models which can generate 15-min interval data for heating, cooling, electricity, and hot water usage of any building in the US from building characteristics, weather timeseries, and occupancy time series.
It has many other non-NLP applications.
Re: A pure NumPy implementation of Mamba
#9Earlier quoted context omitted.
It totally mentions what it does. It takes the sentence "I have a dream that" and extends it to: "I have a dream that I will be able to see the sunrise in the morning." It's an LLM.
It’s much more than just an LLM. The mamba architecture is often used in the backbone of an LLM but you can use it more generally as a linear-time (as opposed to quadratic-time) sequence modeling architecture (as per the original paper’s title, which is cited in the linked repo). It is much closer to a convolutional network or an RNN (it has bits of both) than to a transformer architecture. It is based off the notion…
Would love to hear more about that building energy modelling example, have you done a writeup you could share?
Re: A pure NumPy implementation of Mamba
#10Totally unclear what this is. I scrolled through the readme and it didn't even mention once what it does.
It's an LLM architecture competing with transformers: https://arxiv.org/abs/2312.00752
Proponents of it usually highlight it's inference performance, in particular linear scaling with the input tokens.